Abstractive Multi-document Summarization by Partial Tree Extraction, Recombination and Linearization

Litton J Kurisinkel, Yue Zhang, Vasudeva Varma


Abstract
Existing work for abstractive multidocument summarization utilise existing phrase structures directly extracted from input documents to generate summary sentences. These methods can suffer from lack of consistence and coherence in merging phrases. We introduce a novel approach for abstractive multidocument summarization through partial dependency tree extraction, recombination and linearization. The method entrusts the summarizer to generate its own topically coherent sequential structures from scratch for effective communication. Results on TAC 2011, DUC-2004 and 2005 show that our system gives competitive results compared with state of the art abstractive summarization approaches in the literature. We also achieve competitive results in linguistic quality assessed by human evaluators.
Anthology ID:
I17-1082
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Greg Kondrak, Taro Watanabe
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
812–821
Language:
URL:
https://aclanthology.org/I17-1082
DOI:
Bibkey:
Cite (ACL):
Litton J Kurisinkel, Yue Zhang, and Vasudeva Varma. 2017. Abstractive Multi-document Summarization by Partial Tree Extraction, Recombination and Linearization. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 812–821, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Abstractive Multi-document Summarization by Partial Tree Extraction, Recombination and Linearization (J Kurisinkel et al., IJCNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/I17-1082.pdf